yt_dlp/extractor/zoom.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4
   5 from .common import InfoExtractor
   6 from ..utils import (
   7     ExtractorError,
   8     int_or_none,
   9     js_to_json,
  10     parse_filesize,
  11     urlencode_postdata,
  12     urljoin,
  13 )
  14
  15
  16 class ZoomIE(InfoExtractor):
  17     IE_NAME = 'zoom'
  18     _VALID_URL = r'(?P<base_url>https?://(?:[^.]+\.)?zoom.us/)rec(?:ording)?/(?:play|share)/(?P<id>[A-Za-z0-9_.-]+)'
  19     _TEST = {
  20         'url': 'https://economist.zoom.us/rec/play/dUk_CNBETmZ5VA2BwEl-jjakPpJ3M1pcfVYAPRsoIbEByGsLjUZtaa4yCATQuOL3der8BlTwxQePl_j0.EImBkXzTIaPvdZO5',
  21         'md5': 'ab445e8c911fddc4f9adc842c2c5d434',
  22         'info_dict': {
  23             'id': 'dUk_CNBETmZ5VA2BwEl-jjakPpJ3M1pcfVYAPRsoIbEByGsLjUZtaa4yCATQuOL3der8BlTwxQePl_j0.EImBkXzTIaPvdZO5',
  24             'ext': 'mp4',
  25             'title': 'China\'s "two sessions" and the new five-year plan',
  26         }
  27     }
  28
  29     def _real_extract(self, url):
  30         base_url, play_id = self._match_valid_url(url).groups()
  31         webpage = self._download_webpage(url, play_id)
  32
  33         try:
  34             form = self._form_hidden_inputs('password_form', webpage)
  35         except ExtractorError:
  36             form = None
  37         if form:
  38             password = self.get_param('videopassword')
  39             if not password:
  40                 raise ExtractorError(
  41                     'This video is protected by a passcode, use the --video-password option', expected=True)
  42             is_meeting = form.get('useWhichPasswd') == 'meeting'
  43             validation = self._download_json(
  44                 base_url + 'rec/validate%s_passwd' % ('_meet' if is_meeting else ''),
  45                 play_id, 'Validating passcode', 'Wrong passcode', data=urlencode_postdata({
  46                     'id': form[('meet' if is_meeting else 'file') + 'Id'],
  47                     'passwd': password,
  48                     'action': form.get('action'),
  49                 }))
  50             if not validation.get('status'):
  51                 raise ExtractorError(validation['errorMessage'], expected=True)
  52             webpage = self._download_webpage(url, play_id)
  53
  54         data = self._parse_json(self._search_regex(
  55             r'(?s)window\.__data__\s*=\s*({.+?});',
  56             webpage, 'data'), play_id, js_to_json)
  57
  58         subtitles = {}
  59         for _type in ('transcript', 'cc'):
  60             if data.get('%sUrl' % _type):
  61                 subtitles[_type] = [{
  62                     'url': urljoin(base_url, data['%sUrl' % _type]),
  63                     'ext': 'vtt',
  64                 }]
  65
  66         return {
  67             'id': play_id,
  68             'title': data['topic'],
  69             'url': data['viewMp4Url'],
  70             'subtitles': subtitles,
  71             'width': int_or_none(data.get('viewResolvtionsWidth')),
  72             'height': int_or_none(data.get('viewResolvtionsHeight')),
  73             'http_headers': {
  74                 'Referer': base_url,
  75             },
  76             'filesize_approx': parse_filesize(data.get('fileSize')),
  77         }